Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Fundamental Attribution Error01:14

Fundamental Attribution Error

12.8K
According to some social psychologists, people tend to overemphasize internal factors as explanations—or attributions—for the behavior of other people. They tend to assume that the behavior of another person is a trait of that person, and to underestimate the power of the situation on the behavior of others. They tend to fail to recognize when the behavior of another is due to situational variables, and thus to the person’s state. This erroneous assumption is...
12.8K
Hindsight Biases01:12

Hindsight Biases

3.4K
Hindsight bias leads you to believe that the event you just experienced was predictable, even though it really wasn’t. In other words, you knew all along that things would turn out the way they did. Can you relate this to the phrase "Hindsight is 20/20" now? 
3.4K
Cause and Effect01:53

Cause and Effect

10.9K
While variables are sometimes correlated because one does cause the other, it could also be that some other factor, a confounding variable, is actually causing the systematic movement in our variables of interest. For instance, as sales in ice cream increase, so does the overall rate of crime. Is it possible that indulging in your favorite flavor of ice cream could send you on a crime spree? Or, after committing crime do you think you might decide to treat yourself to a cone?
10.9K
Reason and Intuition01:37

Reason and Intuition

6.4K
The human brain processes information for decision-making using one of two routes: an intuitive system and a rational system (Epstein, 1994; popularized by Kahneman, 2011 as System 1 and System 2, respectively). The intuitive system is quick, impulsive, and operates with minimal effort, relying on emotions or habits to provide cues for what to do next, while the rational system is logical, analytical, deliberate, and methodical. Research in neuropsychology suggests that the...
6.4K
Non-equilibrium in the Cell01:16

Non-equilibrium in the Cell

4.4K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
4.4K
The Availability Heuristic01:08

The Availability Heuristic

5.9K
A heuristic is a general problem-solving framework (Tversky & Kahneman, 1974). You can think of these as mental shortcuts that are used to solve problems. Different types of heuristics are used in different types of situations, and the impulse to use a heuristic occurs when one of five conditions is met (Pratkanis, 1989):
5.9K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Social construction of XAI: Do we need one definition to rule them all?

Patterns (New York, N.Y.)·2024
Same author

Situated language learning via interactive narratives.

Patterns (New York, N.Y.)·2021
Same author

From linear story generation to branching story graphs.

IEEE computer graphics and applications·2006
See all related articles

Related Experiment Video

Updated: Jun 21, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

543

Explainability pitfalls: Beyond dark patterns in explainable AI.

Upol Ehsan1, Mark O Riedl1

  • 1Georgia Institute of Technology, Atlanta GA, USA.

Patterns (New York, N.Y.)
|July 15, 2024
PubMed
Summary
This summary is machine-generated.

Explainability pitfalls (EPs) are unintended negative consequences of AI explanations, distinct from malicious dark patterns. Addressing these EPs is crucial for building trustworthy explainable artificial intelligence (XAI) systems.

More Related Videos

Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses
05:21

Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses

Published on: January 7, 2019

7.9K
Combining Computer Game-Based Behavioural Experiments With High-Density EEG and Infrared Gaze Tracking
13:40

Combining Computer Game-Based Behavioural Experiments With High-Density EEG and Infrared Gaze Tracking

Published on: December 16, 2010

16.7K

Related Experiment Videos

Last Updated: Jun 21, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

543
Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses
05:21

Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses

Published on: January 7, 2019

7.9K
Combining Computer Game-Based Behavioural Experiments With High-Density EEG and Infrared Gaze Tracking
13:40

Combining Computer Game-Based Behavioural Experiments With High-Density EEG and Infrared Gaze Tracking

Published on: December 16, 2010

16.7K

Area of Science:

  • Artificial Intelligence
  • Human-Computer Interaction
  • AI Ethics

Background:

  • Explainable Artificial Intelligence (XAI) systems aim to increase transparency and trustworthiness.
  • Understanding potential negative effects of AI explanations is critical for reliable AI deployment.
  • Existing research often focuses on intentional manipulation, overlooking unintentional harms.

Purpose of the Study:

  • To introduce and define "explainability pitfalls" (EPs) as a novel category of negative effects in XAI.
  • To differentiate EPs from intentionally deceptive "dark patterns."
  • To propose strategies for mitigating EPs in XAI systems.

Main Methods:

  • Conceptual articulation and demarcation of explainability pitfalls.
  • Operationalization of EPs through a case study analysis.
  • Development of multi-level strategies (research, design, organizational) for addressing EPs.

Main Results:

  • Explainability pitfalls represent unanticipated negative downstream effects of AI explanations.
  • These pitfalls can emerge even without user manipulation, leading to issues like unwarranted trust in numerical outputs.
  • A case study demonstrated the emergence of unintended negative effects despite good intentions.

Conclusions:

  • Proactive and preventative strategies are necessary to address EPs at research, design, and organizational levels.
  • Reframing AI adoption, recalibrating stakeholder empowerment, and resisting a "move fast and break things" approach are key implications.
  • Mitigating EPs is essential for fostering genuine trust and responsible innovation in XAI.